Title: Reasoning and mathematics %E2%80%94 Benchmarks | LLM EU
Canonical: https://llmeu.com/pt/benchmarks/reasoning/
Markdown mirror: https://llmeu.com/pt/benchmarks/reasoning.md
Machine-readable: https://llmeu.com/llms.txt (index) - https://llmeu.com/llms-full.txt (full catalogue) - https://llmeu.com/llms-catalogue.json

# Reasoning and mathematics

Matem%C3%A1tica de competi%C3%A7%C3%A3o (AIME) e quest%C3%B5es de ci%C3%AAncias de n%C3%ADvel de p%C3%B3s-gradua%C3%A7%C3%A3o (GPQA), conforme publicado pelos editores do modelo. Estes s%C3%A3o os benchmarks mais frequentemente citados para modelos de racioc%C3%ADnio e os mais sens%C3%ADveis %C3%A0s configura%C3%A7%C3%B5es de amostragem.

Every score in this set is republished from the model publisher%E2%80%99s own model card or vendor report and names that source per entry. LLM EU has run no evaluation, has not reproduced any score, and has not verified the harness settings. Vendor-reported numbers are self-reported and are labelled as such on the model cards. AIME and GPQA scores are sampling-sensitive: number of samples, temperature and tool access are stated on the individual model cards and are not uniform across these rows.